Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1072 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Event Sequencing | VECTOR L2 (Ne=8) 1.0 (test) | 26 | Feb 26, 2026 | ||
| Event Sequencing | VECTOR L1 (Ne=4) 1.0 (test) | 26 | Feb 26, 2026 | ||
| MCI vs. AD classification | ADNI | 26 | Jun 19, 2026 | ||
| Overall Performance | Average across all benchmarks | 26 | Jun 11, 2026 | ||
| Stable Grasp Reconstruction | HOT3D-HIT (test) | 26 | Feb 26, 2026 | ||
| End-to-End Text Spotting | Real-Text | 26 | Feb 26, 2026 | ||
| Text Detection | Real-Text | 26 | Feb 26, 2026 | ||
| Audio-Visual Perception | WorldSense | 26 | Jul 7, 2026 | ||
| Multimodal Reasoning | MMVP | 26 | May 19, 2026 | ||
| 4D Occupancy forecasting | nuScenes | 26 | Jun 11, 2026 | ||
| Math Reasoning | We-Math | 26 | May 22, 2026 | ||
| Math Reasoning | MathVista | 26 | May 22, 2026 | ||
| Mathematical Reasoning | MMStar Math | 26 | Jun 17, 2026 | ||
| Multimodal Understanding | MMStar (test) | 26 | May 4, 2026 | ||
| Emotion Recognition (ER) Valence and Arousal Regression | EMER (test) | 26 | Feb 26, 2026 | ||
| Multimodal Question Answering | MMBench en (test) | 26 | Apr 7, 2026 | ||
| Localization | RefCOCOg (val) | 26 | Feb 26, 2026 | ||
| Localization | RefCOCO+ (testB) | 26 | Feb 26, 2026 | ||
| Localization | RefCOCO+ (testA) | 26 | Feb 26, 2026 | ||
| Image Captioning | MSCOCO | 26 | May 15, 2026 | ||
| Global human motion estimation | RICH | 26 | Jul 1, 2026 | ||
| Medical Image Segmentation | DRIVE (test) | 26 | Feb 26, 2026 | ||
| Face Attribute Recognition | LFWA | 26 | Feb 26, 2026 | ||
| Spatial Reasoning | Escher-Bench 1.0 (test) | 26 | Feb 26, 2026 | ||
| Audio-Driven Facial Animation | MEAD 41 (test) | 26 | Feb 26, 2026 |